© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109431
    Prev
    Next
    INDEX
    Explanations

    AI related technical topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gold
    0.50
     gold
    0.49
     yellow
    0.47
    Gold
    0.46
    褪
    0.44
     yellows
    0.44
    Yellow
    0.42
     żół
    0.42
     Yellow
    0.41
     blond
    0.41
    POSITIVE LOGITS
    निर
    0.42
     ลํา
    0.42
    rootScope
    0.41
    サスカ
    0.40
     inscreve
    0.40
    ∘
    0.40
     முன்ன
    0.38
    lmp
    0.38
    বেশ
    0.38
    cnf
    0.38
    Activations Density 0.001%

    No Known Activations